© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40659
    Prev
    Next
    INDEX
    Explanations

    stretch marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    শ্রেণীর
    0.50
    ب
    0.46
     Universal
    0.45
    o
    0.45
    ة
    0.44
     कमे
    0.43
    マー
    0.43
     উপার্জন
    0.42
    通勤
    0.42
     Hyper
    0.42
    POSITIVE LOGITS
     heifers
    0.47
     הז
    0.45
     stork
    0.44
     שט
    0.43
     [],
    0.43
     workshops
    0.42
    Pues
    0.41
     ব্যবস্থা
    0.40
     sighting
    0.39
     שנה
    0.39
    Activations Density 0.001%

    No Known Activations